In this paper, we propose a new approach to learn multimodal multilingual embeddings for matching images and their relevant captions in two languages. We combine two existing objective functions to make images and captions close in a joint embedding space while adapting the alignment of word embeddings between existing languages in our model. We show that our approach enables better generalization, achieving state-of-the-art performance in text-to-image and image-to-text retrieval task, and caption-caption similarity task. Two multimodal multilingual datasets are used for evaluation: Multi30k with German and English captions and Microsoft-COCO with English and Japanese captions.
@article{arxiv.1910.03291,
title = {Aligning Multilingual Word Embeddings for Cross-Modal Retrieval Task},
author = {Alireza Mohammadshahi and Remi Lebret and Karl Aberer},
journal= {arXiv preprint arXiv:1910.03291},
year = {2020}
}